ingest_html

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It discloses a non-obvious behavioral trait: the output is a structural blueprint, not an exact reproduction ('Not a 1:1 clone'), and it lists exactly which elements are captured. This provides solid, actionable expectations for the agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no superfluous text. The action and resource are front-loaded, and the key caveat ('Not a 1:1 clone') is placed at the end, ensuring each sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers input, processing, output scope, and a downstream step (new_section). With no output schema, it could detail the blueprint's exact structure more, but for a one-parameter tool with clear intent, it is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already documents the single parameter with 100% coverage ('Raw HTML to analyse'). The description adds value by qualifying the input as 'reference HTML', implying it's a sample for design extraction, and by linking the output to rebuilding sections, which enriches the parameter's purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific verb ('Parse'), a clear resource ('reference HTML'), and a distinct outcome ('structural blueprint' with explicit list of elements). It also differentiates from a simple clone by stating 'Not a 1:1 clone', which clarifies what the tool does not do.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by stating 'Parse reference HTML' and suggests a concrete workflow: 'you can rebuild as BuilderX sections with new_section'. It does not explicitly mention when to avoid this tool or compare with ingest_url, but the context makes the intended scenario clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.